Load Scikit-Learn Dataset as Pandas DataFrame

Scikit-Learn offers several datasets to play around with - most of them being toy datasets to learn from and test things out.

Some beginners find the comfort of a tabular Pandas DataFrame format more intuitive than NumPy arrays. Thankfully, you can import a dataset as a Bunch object containing a DataFrame by setting as_frame to True:

import pandas as pd
import numpy as np
from sklearn.datasets import fetch_california_housing

data = fetch_california_housing(as_frame=True)

This Bunch object contains data and target our "X" and "y", but they're separate! The data field is a DataFrame:

data.data

While our target is a Series:

data.target

0        4.526
1        3.585
2        3.521
3        3.413
4        3.422
         ...  
20635    0.781
20636    0.771
20637    0.923
20638    0.847
20639    0.894
Name: MedHouseVal, Length: 20640, dtype: float64

The easiest way to combine them is to simply assign the series to a DataFrame:

df = data.data.assign(MedHouseVal=data.target)
df

This results in:

Or, you can create a new frame, with the data and feature_names, adding the target by simply assigning it to a new column:

df = pd.DataFrame(data=data.data, columns=data.feature_names)
df['MedHouseVal'] = data.target
df